Showing papers by "Charles R. Dyer published in 1991"
02 Jun 1991
TL;DR: The authors provide a critique of the aspect graph approach that describes a graph structure in which each node represents a general view of the object as seen from some maximal, connected cell of viewpoint space.
Abstract: The aspect graph of an object is a graph structure in which each node represents a general view of the object as seen from some maximal, connected cell of viewpoint space; each arc represents an accidental view (or visual event) which occurs on the boundary between two cells of general viewpoint; there is a node for each possible general view of the object, and there is an arc for each possible visual event. The authors provide a critique of the aspect graph approach. >
37 citations
03 Jun 1991
TL;DR: Using ST surface flow, i.e., the extension of optical flow to ST surfaces, it is shown how ST flow curves can be recovered and then used to detect groups of flow curves such that each group represents a single object or surface in the scene undergoing motion.
Abstract: A spatiotemporal (ST) image cube, created by stacking a temporally dense sequence of images together, is a temporally coherent data representation. Using ST surface flow, i.e., the extension of optical flow to ST surfaces, it is shown how ST flow curves can be recovered and then used to detect groups of flow curves such that each group represents a single object or surface in the scene undergoing motion. The algorithm forms clusters of similar flow curves and is based on constraints called the temporal uniqueness constraints. First, a point in an image can only move to at most one point in the next image. Second, a point in an image can come from at most one point in the previous image. When these constraints are violated, or it appears that they are violated, occlusion or disocclusion has occurred and therefore can also be detected. Successful grouping of coherent regions of the ST cube for two gray-level image sequences is shown. >
24 citations
02 Jun 1991
TL;DR: The paper addresses the problem of how to constrain the set of viewpoints from which a 3D model will project to a given a set of occluding contour features with a new approach that relies on a precomputed occluded contour representation for polyhedral models that makes T-junctions, contour terminals and the change in contour topology explicit.
Abstract: The paper addresses the problem of how to constrain the set of viewpoints from which a 3D model will project to a given a set of occluding contour features. The approach is new in that it relies on a precomputed occluding contour representation for polyhedral models that makes T-junctions, contour terminals and the change in contour topology explicit. Potential model-image correspondences of occluding contour features can be formulated as regions in viewpoint space defined by constraint boundaries since features are only visible from a restricted set of viewpoints. The implementation results demonstrate that T-junction features can efficiently constrain the space of viewpoints to produce a small, bounded viewpoint set that accounts for the occluding contour features. >
12 citations
01 Apr 1991
TL;DR: A description of the change in appearance of the rim and occluding contour as a function of viewpoint allows the organization of features of the occluded contour for indexing and matching in a dynamic context where image features are changing over time and a static context where matching methods must iteratively refine an estimation of viewpoint.
Abstract: This paper introduces a novel, viewer-centered approach to modeling the geometry of the visible occludingcontour of solid 3D shape. A description of the change in appearance of the rim and occluding contour as a functionof viewpoint allows the organization of features of the occluding contour for indexing and matching. This organiza-tion makes the features of the occluding contour explicit for matching in a dynamic context where image features are changing over time, and in a static context where matching methods must iteratively refine an estimation of viewpoint. The rim appearance representation models the exact appearance of the occluding contour formed by the edges of a polyhedron that is assumed to be an approximation of a smooth shape. An algorithm is presented for constructing the rim appearance representation. Bounds on space and time are given, and implementation resultsshow that the rim appearance representation is significantly smaller than the aspect graph and the aspect representa-tion.
5 citations